List skills
Agent-assisted maintainership and development framework for Apache projects — Triage, Mentoring, Drafting (agent-authored fixes with human review), and Pairing (developer-side dev-cycle) skills shipping; Agentic Autonomous (auto-merge) on the roadmap.
npx -y skills add apache/magpie --skill list-skillsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
What its author says it does
Copied from the file, not written here
Print a human-readable index of every skill in this repository, grouped by family prefix (`pr-management`, `security`, `setup`, …) with each skill's name and the first sentence of its `description`. The listing is generated on every run from the live `.claude/skills/*/SKILL.md` files, so it never goes stale when skills are added, removed, or rewritten.
The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
4.1 KB, as published. Nobody here has run it
list-skills
Print a human-readable index of the skills in this repository.
The index is generated on every run from the live
.claude/skills/*/SKILL.md files — there is no cached copy to
keep in sync. The skill exists for humans (newcomers reading the
repo, maintainers checking what is available); agents route
invocations via the same frontmatter the script reads, so this
skill is purely informational.
Prerequisites
- Python 3.9+ on
PATHwithPyYAMLimportable. The framework's Python toolchain already meets this; no extra setup.
Step 1 — Run the listing script
Run the bundled script and present its output to the user verbatim:
python3 .claude/skills/magpie-list-skills/scripts/list_skills.py
For a layout that puts each description on its own indented line
(easier to read when descriptions are long), pass --verbose:
python3 .claude/skills/magpie-list-skills/scripts/list_skills.py --verbose
The script:
- walks
.claude/skills/*/SKILL.mdrelative to its own location; - parses each skill's YAML frontmatter for
name+description; - groups skills by family prefix (the first hyphen-separated
token, with
pr-managementrecognised as a two-token family — seeKNOWN_TWO_TOKEN_FAMILIES); - prints each skill with the first sentence of its description.
When a new multi-token family appears (e.g. a hypothetical
docs-build-*), add the prefix to KNOWN_TWO_TOKEN_FAMILIES in
scripts/list_skills.py; otherwise the
new skills land under the single-token head.
Step 2 — Hand the output to the user
Quote the script output back to the user as-is. Do not
paraphrase, summarise, or re-order — the value of this skill is
that the listing is the canonical, deterministic view of what
exists. If the user asks for more detail on a specific skill,
read that skill's SKILL.md and answer from it.
Hard rules
- Read-only. This skill never edits, creates, or deletes
files. It only reads
SKILL.mdfiles under.claude/skills/. - No paraphrasing. Always present the script output verbatim. Paraphrasing reintroduces the staleness this skill exists to prevent.
References
scripts/list_skills.py— the listing script Step 1 invokes.AGENTS.md— the framework's "Reusable skills" section, which explains the.claude/skills/layout and frontmatter convention.write-skill— sibling skill for authoring a new skill. Use it when the listing reveals a gap that warrants a new entry.